© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 72870
    Prev
    Next
    INDEX
    Explanations

    nearest

    np_max-act · gemini-2.0-flash

    mathematical expressions and calculations involving rounding and precision.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on the exact decimal numbers used as rounding‐precision parameters (e.g. “3.21875,” “4.3203125,” “3.3515625,” etc.) in “rounded to the nearest X” instructions.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ou
    -0.07
    ертв
    -0.07
     vc
    -0.06
    malı
    -0.06
    .ncbi
    -0.06
     sequences
    -0.06
    oglobin
    -0.06
    iв
    -0.06
    ANK
    -0.06
    artifact
    -0.06
    POSITIVE LOGITS
     después
    0.07
     RBI
    0.07
     уча
    0.07
     uyar
    0.06
    ingle
    0.06
     área
    0.06
     نگاه
    0.06
     Premiere
    0.06
     民
    0.06
     الاقتص
    0.06
    Activations Density 0.001%

    No Known Activations